You say it. It researches.
Describe your stock-picking ideas in natural language
AI automatically validates, backtests, and gives you answers
"Find stocks with consecutive revenue growth"
Free to use · 900+ indicators for instant backtesting
Before & After
From coding to plain language
Write code, learn APIs, tune parameters
2-4 weeks learning curve, error-prone
import finlab as fl
from finlab import data
close = data.get('price:收盤價')
rev = data.get('monthly_revenue:當月營收')
rev_growth = rev.pct_change(12)
cond1 = rev_growth > 0.2
cond2 = close == close.rolling(60).max()
cond3 = data.get('price:成交股數') * close > 1e8
position = cond1 & cond2 & cond3
report = fl.backtest(position)
report.display()Describe in plain language, AI handles everything
Instant backtesting, results in 3 seconds
Input:
"Find stocks with revenue growth > 20% YoY, 60-day price high, and daily volume > $100M"
Live Demo
Say it, see results
Actual interface — from description to results in under 30 seconds
By the Numbers
Verified Results
Verified Strategy Performance
| Strategy | CAGR | Sharpe | Max DD | Win Rate |
|---|---|---|---|---|
| Momentum | 32.4% | 1.31 | -15.2% | 68.7% |
| F-Score | 28.1% | 1.18 | -18.4% | 71.2% |
| Low Volatility | 22.7% | 1.42 | -8.9% | 74.1% |
| Red Packet | 19.8% | 0.97 | -21.3% | 65.8% |
| Reversal | 24.5% | 1.15 | -16.7% | 63.4% |
| Small-Cap Effect | 35.2% | 1.08 | -24.1% | 66.9% |
Backtest period 2019-01 to 2024-12 | Excluding transaction costs | Past performance does not guarantee future results
Not a promise — verified results
Others have already done it
“營收加速選股法”
“年化24%實戰”
“32.8%自動挖掘”
38 verified strategies — which one is your starting point?
Browse All Strategy ResearchReal User Voices
They're already using FinLab
“What would I do without FinLab for investing? The thought alone scares me”
Integrates ML, factor analysis, and backtest performance
Individual Investor
Almost daily
“So many strategy examples to learn from — even beginners can get started. No need to invent strategies from scratch”
Just tweak or combine and test
Individual Investor
Several times a week
“Just looking at the data format and processing, you can tell the developers actually trade”
TEJ's data format and API are terrible in comparison
Individual Investor
Almost daily
“Absorbed trading logic from multiple example strategies — any feature I need, I can find the code right away”
Standing on the shoulders of giants
Individual Investor
Almost daily
“Saves me from debugging web scrapers myself, makes ML much more accessible”
Affordable and practical
Individual Investor
Almost daily
From 226 user surveys · Real NPS promoter feedback
Three Steps to Start Profiting
Choose your method
Install
One command, supports 37+ AI tools
Describe
Describe your stock-picking ideas in natural language
"Find low PE, high dividend yield stocks, exclude financials"
Profit
Instant backtest results and stock picks
CAGR
24.5%
Sharpe
1.18
FAQ
Frequently Asked Questions
FinLab AI is a Taiwan stock quantitative trading research platform. Describe your stock-picking ideas in natural language, and AI automatically builds strategies, backtests, and validates — no coding required.
Not at all. Simply describe your stock selection logic in plain language, like "Find stocks with consecutive revenue growth." FinLab AI will automatically generate and backtest the strategy. Advanced users can also customize strategies using Python.
The free tier provides 900+ Taiwan stock historical data for backtesting. VIP (NT$749/month) adds daily data updates, full portfolio analysis, auto-scheduled strategy execution, and complete source code for all strategy articles.
FinLab AI offers 900+ Taiwan stock data indicators covering fundamentals (revenue, EPS, PE ratio), technicals (moving averages, RSI, MACD), and institutional data (foreign/domestic investment, margin trading). Data sourced from TWSE and MOPS.
Backtests use real historical data simulation including transaction costs and slippage. We provide CAGR, Sharpe ratio, max drawdown, and other risk metrics for comprehensive strategy evaluation. Note: past performance does not guarantee future results — please evaluate investment decisions carefully.
Two ways: (1) Open studio.finlab.tw and describe strategies directly in the browser — zero installation. (2) Run curl -sSf https://ai.finlab.finance/install.sh | sh in your terminal to use with Claude Code, Codex, and 37+ AI tools. Advanced users can also install the Python package with pip install finlab.
No coding. No cost.
Just one sentence.
52 strategies all started with one sentence. What's yours?
Start Free